Open Set Relation Extraction via Unknown-Aware Training
This addresses the realistic scenario in relation extraction where models must handle unseen relations, though it is incremental as it builds on existing adversarial techniques for open-set tasks.
The paper tackles the problem of open-set relation extraction, where unknown relations appear at test time, by proposing an unknown-aware training method that synthesizes difficult negative instances via adaptive perturbations, achieving state-of-the-art unknown relation detection without harming known relation classification.
The existing supervised relation extraction methods have achieved impressive performance in a closed-set setting, where the relations during both training and testing remain the same. In a more realistic open-set setting, unknown relations may appear in the test set. Due to the lack of supervision signals from unknown relations, a well-performing closed-set relation extractor can still confidently misclassify them into known relations. In this paper, we propose an unknown-aware training method, regularizing the model by dynamically synthesizing negative instances. To facilitate a compact decision boundary, ``difficult'' negative instances are necessary. Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations. Experimental results show that this method achieves SOTA unknown relation detection without compromising the classification of known relations.